[ICLR 2026🔥] MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
☆151May 19, 2026Updated 2 months ago
Alternatives and similar repositories for MHLA
Users that are interested in MHLA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICCV2025 highlight]Rectifying Magnitude Neglect in Linear Attention☆63Jul 24, 2025Updated last year
- [ICML 2026🔥]Rethinking Video Generation Model for the Embodied World☆91Jun 1, 2026Updated 2 months ago
- Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers☆42Jul 1, 2026Updated last month
- HumanNet: Scaling Human-centric Video Learning to One Million Hours☆280May 26, 2026Updated 2 months ago
- Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders☆255Feb 13, 2026Updated 5 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Official implementation of MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement (ICLR2026)☆300Mar 24, 2026Updated 4 months ago
- [TIP 2026] "FourierSR: A Fourier Token-based Plugin for Efficient Image Super-Resolution"☆17Feb 4, 2026Updated 6 months ago
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention☆326Feb 24, 2026Updated 5 months ago
- 📷 [CVPR'26] Camera-controlled text-to-video generation, now with intrinsics, distortion and orientation control!☆215May 15, 2026Updated 2 months ago
- [AAAI 2026] Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment☆16Dec 9, 2025Updated 7 months ago
- [CVPR 2026🔥] Enhancing Spatial Understanding in Image Generation via Reward Modeling☆86Mar 2, 2026Updated 5 months ago
- Minute-long video generation at 24FPS.☆69Mar 28, 2026Updated 4 months ago
- [CVPR 2026 Highlight] Official implementation of Log-linear Sparse Attention (LLSA).☆93May 1, 2026Updated 3 months ago
- [ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactiv…☆897Jul 23, 2026Updated last week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Flow Map OPD for AnyStep Video Diffusion☆404May 23, 2026Updated 2 months ago
- Video models as pure visual reasoners for high-quality text-to-image generation via Chain-of-Frame reasoning.☆39Jan 16, 2026Updated 6 months ago
- Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"☆64Jul 1, 2025Updated last year
- [2025] ModalFormer: Multimodal Transformer for Low-Light Image Enhancement☆27Apr 14, 2026Updated 3 months ago
- Code Implementation of "WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation"☆179May 9, 2026Updated 2 months ago
- Vision Bridge Transformer at Scale☆147Dec 1, 2025Updated 8 months ago
- [ICML 2026] "LIVE: Long-horizon Interactive Video World ModEling"☆35Jul 15, 2026Updated 2 weeks ago
- [CVPR 2026 Findings] Official repository for "SAT: Selective Aggregation Transformer for Image Super-Resolution"☆37Jun 1, 2026Updated 2 months ago
- rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale☆778Jun 25, 2026Updated last month
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- [ICML 2026] Stable Velocity: A Variance Perspective on Flow Matching☆29Feb 19, 2026Updated 5 months ago
- [ICLR’26] Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control☆108Feb 8, 2026Updated 5 months ago
- Official PyTorch implementation of [PSA: Pyramid Sparse Attention for Efficient Video Understanding and Generation](https://arxiv.org/abs…☆25Jan 25, 2026Updated 6 months ago
- [AAAI 2026] Official repository of Circulant Attention☆65Jun 26, 2026Updated last month
- [CVPR2026] VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice☆89Feb 27, 2026Updated 5 months ago
- Official Implementation of "MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives"☆216Dec 29, 2025Updated 7 months ago
- [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving☆289Aug 4, 2025Updated last year
- [ICLR 2025] This repo is the official implementation of "The Labyrinth of Links: Navigating the Associative Maze of Multi-modal LLMs".☆13Jan 25, 2025Updated last year
- [CVPR 2026] Official repo for "EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation"☆61Mar 13, 2026Updated 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICML 2026] ReCo: In-Context Generation with Regional Constraints for Instructional Video Editing☆172May 26, 2026Updated 2 months ago
- PyTorch Implementation of LocAtViT in "Locality-Attending Vision Transformer" (ICLR 2026)☆19Mar 10, 2026Updated 4 months ago
- StableWorld: Towards Stable and Consistent Long Interactive Video Generation☆97Mar 18, 2026Updated 4 months ago
- [ICLR 2026] Official implementation of "Enhancing Multi-Image Understanding Through Delimiter Token Scaling"☆16Jul 10, 2026Updated 3 weeks ago
- Code for "StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion Model", AAAI2026 Oral☆55Jun 15, 2026Updated last month
- This code implements the algorithm of FIPO, a value-free RL recipe for eliciting deeper reasoning from a clean base model.☆18Jul 14, 2026Updated 3 weeks ago
- Image-Free Timestep Distillation via Continuous-Time Consistency with Trajectory-Sampled Pairs☆21Dec 16, 2025Updated 7 months ago